The News in Earnings Announcement Disclosures: Capturing Word Context Using LLM Methods

This paper is based on the author’s dissertation titled “Contextualized News in Corporate Disclosures: A Neural Language Approach.” The author thanks the dissertation committee for insightful guidance: Peter Wysocki (chair), Francois Brochet, Dokyun Lee, and Eddie Riedl. The author thanks Suraj Srinivasan (department editor), an anonymous associate editor, and two anonymous reviewers for thoughtful comments; workshop participants at the 2021 AAA (American Accounting Association)/Deloitte Foundation/J. Michael Cook Doctoral Consortium, 2023 FARS (Financial Accounting and Reporting Section) Meeting, 2023 SARAC (Swiss Accounting Research Alpine Camp), 2023 HARC (Hawaii Accounting Research Conference), Bocconi University, Boston University, INSEAD, Northeastern University, Northwestern University, The Ohio State University, The University of Texas at Dallas, Universidad Carlos III de Madrid, University of Kentucky, University of Washington, and University of Wisconsin-Madison for valuable comments and discussions; and Daniel Bens, Oliver Binz, Elizabeth Blankespoor, Ed deHaan, Ronald Dye, Nargess Golshan, Charles Lee, Maria Loumioti, Russell Lundholm, Matthew Lyle, Stanimir Markov, Miguel Minutti-Meza (Discussant), Darren Roulstone, Sugata Roychowdhury, Gil Sadka, Jason Schloetzer, Shiwon Song, Dan Stone, Stephen Stubben, Andrew Van Buskirk, and Daniel Wangerin.